| """MagicBERT configuration for HuggingFace transformers.""" | |
| from transformers import PretrainedConfig | |
| class MagicBERTConfig(PretrainedConfig): | |
| """Configuration class for MagicBERT model. | |
| MagicBERT is a BERT-style transformer model designed for binary file | |
| type classification. It uses a byte-level BPE tokenizer with a 32K vocabulary. | |
| """ | |
| model_type = "magic-bert" | |
| def __init__( | |
| self, | |
| vocab_size: int = 32768, | |
| hidden_size: int = 512, | |
| num_hidden_layers: int = 8, | |
| num_attention_heads: int = 8, | |
| intermediate_size: int = 2048, | |
| hidden_dropout_prob: float = 0.1, | |
| attention_probs_dropout_prob: float = 0.1, | |
| max_position_embeddings: int = 512, | |
| pad_token_id: int = 2, | |
| hidden_act: str = "gelu", | |
| layer_norm_eps: float = 1e-12, | |
| **kwargs, | |
| ): | |
| super().__init__(pad_token_id=pad_token_id, **kwargs) | |
| self.vocab_size = vocab_size | |
| self.hidden_size = hidden_size | |
| self.num_hidden_layers = num_hidden_layers | |
| self.num_attention_heads = num_attention_heads | |
| self.intermediate_size = intermediate_size | |
| self.hidden_dropout_prob = hidden_dropout_prob | |
| self.attention_probs_dropout_prob = attention_probs_dropout_prob | |
| self.max_position_embeddings = max_position_embeddings | |
| self.hidden_act = hidden_act | |
| self.layer_norm_eps = layer_norm_eps | |